Deskly by Datics AI
Staff ask in plain words. Answers come from your policies, with the source.
Front desk and clinical staff ask about insurance rules, procedures and policies in plain words. Answers come from the practice's own documents, with the source, and only what each role may see.
Built into your codebase and shipped under your name, on an engine we license to you.
app.acmedental.example/help/policies
Acme Dental · Deskly
DemoDoes Bluecrest PPO cover a second cleaning in six months?
Answered from the practice's documents
- Source shown for every answer
- No guess when the documents are silent
Front desk role3 documents searchedHandoff offered
Try it step by stepIllustrative demo on a fictional practice. Not client work.
Try it step by step
Deskly on a fictional practice.
Acme Dental (fictional). Step through the conversation, then see what Deskly hands back, the way your Build Sprint would build it on synthetic data.
app.acmedental.example/help/policies
Acme Dental · Deskly
DemoStep 1 of 5
Illustrative demo on a fictional practice. Not client work.
What it hands back
app.acmedental.example/help/policies
Answer · Front desk
Acme Dental · searched 3 documents this role may read
- Question
- Second cleaning in six months under Bluecrest PPO?
- Done
- Answer
- Two cleanings a calendar year, at least five months apart
- Done
- Source
- Bluecrest PPO guide, page 3 · updated in March
- Done
- Not searched
- Cancellation policy (managers only)
- Check
Answers come only from the practice's documents, with the source. When nothing covers a question, it hands off.
Illustrative demo on a fictional practice. Not client work.
What it does
What Deskly can do.
An assistant inside your product that answers staff questions on insurance rules, procedures and office policies from each practice's own documents, shows the source, respects each role, and hands off when nothing covers the question.
Cited answers
Every answer shows the document and section it came from.
Role-aware
The front desk never sees what only the office manager may see.
Clean handoff
When nothing covers the question, it says so and names who can answer.
Per practice library
Each practice's documents stay separate from every other practice's.
How it works
Each practice's documents are indexed separately, searched only within what the user's role may see, and the model answers only from what was found, with the source.
Built on a cited answers engine we have delivered for document heavy products.
WikiTeq
AI engine · Cited answers
WikiTeq's self hosted AI chat now answers from its documents, citing every source
The chat could not answer from the firm's own documents. Now a separate retrieval service feeds it passages and shows the source of each answer.
NenoDoc Lexicon by Neno Technologies
AI engine · Cited answers
Archive teams get cited answers in French and English on one client-owned GPU
Sensitive archives could not go to an outside AI. Now teams ask in French or English and get answers cited to the page, all on the client's GPU.
Our own product
AI engine · Answers from your own content
Support chats answered from each company's own content, with handoff to a person
Bots that answer from the wrong content lose visitors. Each chatbot in our assistant answers from its own knowledge base and hands off to an agent.
Why it sells
What Deskly does for your business.
What your practices get, and what it does for your renewals and pricing.
Every practice has the problem
Every office has binders nobody reads.
Low risk to start
It answers staff, not patients, and shows its sources.
New staff productive sooner
New front desk staff find answers on day one instead of waiting for the office manager.
Controls
What Deskly touches, and who approves.
Your practices' data is not used to train models for anyone else and stays in your cloud. Built and tested on synthetic or test data.
Who uses it
Front desk, clinical staff, office managers
What it connects to
The practice's own policies, procedures and payer documents
What a person approves
Admins choose which documents each role may search
Switch per practice
On or off for each practice, with data settings their admins control.
How to get it
Two steps to a finished Deskly.
Start with a three-week Build Sprint. Add more only if you want it.
First · Build Sprint · $10,000 fixed
Staff get policy answers without interrupting the office manager
- Cited answers
- Role-aware
- Clean handoff
- In your staging, behind a feature flag
- Delivered as pull requests
- A test set your team reviews
- Week 1Setup
- Weeks 2 to 3Build
- You getDeskly in your staging and a fixed production quote
- Your time
- About 2 to 3 hours a week from a product owner
- Data
- Synthetic or test data, never your practices' customers
- The fee
- Counts toward production
Then · Live in production
A finished product, yours to run
- Fixed quote
- Tested before launch
- Switch per practice
- A finished, working Deskly in your product
- Runs in your cloud, under your name
- Fixed quote, agreed before we start
Optional · Add more later
Only if you want it
More of Deskly:
- Per practice library
Another module:
- Each one quoted on its own
- Nothing ongoing unless you ask
Already built or tried AI? Get it scored with the AI Scorecard. Need something else? Start with a Planning Sprint.
FAQ
Questions about Deskly.
Can it answer patients too?
It can, after staff use has been tested. We start with staff because the risk is lower.
Who decides what each role can see?
Practice admins choose which documents each role may search; the assistant never searches the rest.
What if a policy changes?
Upload the new version; answers come from the current document and show it.
See Deskly on your own product.
Bring your product and one workflow. In 30 minutes we look at where Deskly fits, what it would cost to serve and what your practices' security review will ask.
Calls run in US Central time. No generic AI presentation: we discuss your product, users and production constraints.